docs(esh-ml1): whole-novel embedding bench — gateway-bound, esh-ml1 ~2.2x slower only on the direct path

servers/esh-ml1/README.md

@@ -65,6 +65,22 @@ sites. One fv-ml1 rep of the gateway-vantage rerank burst stalled to 1.0 req/s
 **Consequence: keep esh-ml1 as failover, don't load-share** — sharing would
 roughly double rerank latency for half the fleet's calls.
 
+**Whole-novel embedding, measured 2026-09-25 0653–0717 PT** — *The Stand*
+(uncut, ~1,150 pages): 470,783 words, 12,814 `<p>` paragraphs (median 22 words),
+617,833 tokens. Client on nh3-dev (where worldtree-gateway runs); 3 reps each:
+
+| how | fv-ml1 | esh-ml1 |
+|---|---|---|
+| via gateway, 1 paragraph per request (1,000-para sample, scaled) | 59.8 ms/para → ~12.8 min | 55.3 ms/para → ~11.8 min |
+| via gateway, 64 per request, 1 at a time | 100–123 s | 91–100 s |
+| via gateway, 64 per request, 4 in flight | 46–54 s | 45–50 s |
+| direct to the seat, 64 per request, 4 in flight | 13.4–14.1 s | 28.8–29.6 s |
+
+Through the gateway the GPU is not the bottleneck: one-per-request is network +
+LiteLLM overhead, and batched runs pinned LiteLLM at ~76% CPU (64×1024-float
+JSON per response). Only the direct path shows the card: esh-ml1 is ~2.2×
+slower, ~21k vs ~45k tokens/s.
+
 **VRAM:** 0.20 × 16,380 MiB each; 4,823 MiB in use with both loaded, ~11 GB
 free.